← 研踪 PaperTrailACL Anthology · ACL 2026:acl:2026.acl-demo.38 · 记录 #1
mllm-shap: A Shapley Value Explainability Platform for Text-Audio Multimodal Large Language Models
来源日期（仅到月份） 2026-07
来源记录日期 2026-07
雷达观测 2026-11-01 22:08
摘要
We present mllm-shap, an open-sourcePython platform for researchers and ML practitioners that extends Shapley value (SV)explainability from text-only large languagemodels to multimodal LLMs (MLLMs) thatjointly process text and audio. Buildingon the token-level SV framework introducedby TokenSHAP, mllm-shap addresses threechallenges absent in the text-only setting:(1) modality-aware coalition masking thathandles the coexistence of text tokens anddense audio encoder frames within a single input, (2) multi-turn conversation tracking withper-token role and modality metadata, and(3) audio token grouping via phonetic alignment that reduces the coalition space by 10–50 times. The platform ships as a pip-installablepackage implementing five SV estimation strategies – including a Complementary Contributions estimator with Neyman-optimal allocation that outperforms Monte Carlo baselines – together with an interactive web GUIfor real-time attribution visualization. Toour knowledge, mllm-shap is the first publicly available framework for complete, reproducible SV-based explainability of text-audioMLLMs. The package is MIT-licensed withfull source code on GitHub and a demonstration video included as supplementary material.
论文发现出处
这些页面提供论文线索，不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化，不是作者修订号。来源日期仅到月份或年份时，按该月或该年首日存档。
记录 #1 · 2026-07 · 最新观测版本
mllm-shap: A Shapley Value Explainability Platform for Text-Audio Multimodal Large Language Models
We present mllm-shap, an open-sourcePython platform for researchers and ML practitioners that extends Shapley value (SV)explainability from text-only large languagemodels to multimodal LLMs (MLLMs) thatjointly process text and audio. Buildingon the token-level SV framework introducedby TokenSHAP, mllm-shap addresses threechallenges absent in the text-only setting:(1) modality-aware coalition masking thathandles the coexistence of text tokens anddense audio encoder frames within a single input, (2) multi-turn conversation tracking withper-token role and modality metadata, and(3) audio token grouping via phonetic alignment that reduces the coalition space by 10–50 times. The platform ships as a pip-installablepackage implementing five SV estimation strategies – including a Complementary Contributions estimator with Neyman-optimal allocation that outperforms Monte Carlo baselines – together with an interactive web GUIfor real-time attribution visualization. Toour knowledge, mllm-shap is the first publicly available framework for complete, reproducible SV-based explainability of text-audioMLLMs. The package is MIT-licensed withfull source code on GitHub and a demonstration video included as supplementary material.
查看此版本解读 →查看此版本原文 ↗